gallery: group QAT, APEX and cross-backend builds under their base entry (#10983)

feat(gallery): group 21 more model families under variants Second variant-grouping sweep. QAT and APEX builds are now treated as quantization techniques rather than distinct weights, per maintainer ruling, so they group with their base entry instead of standing alone. Adds 15 new families: quantization and serving-config pairs for llama-3.2-1b/3b-instruct, dolphin-2.9-llama3-8b, phi-2-chat, ideogram-4, meta-llama-3.1-8b-instruct, omnivoice-cpp and qwen3-tts-cpp; the gemma-3 4b/12b/27b QAT families; and three cross-backend pairs (silero-vad plus its sherpa-onnx build, and the vibevoice TTS and ASR builds shared between the vibevoice-cpp and crispasr backends). The cross-backend pairs are the first entries that meaningfully exercise engine-preference ranking during auto-selection. Restructures four gemma-4 families (31b-it, 26b-a4b-it, e2b-it, e4b-it). Those bare entries were skipped by the first sweep, which left a QAT build as parent by default. The bare entry is what installs when nothing else fits, so it reclaims the parent slot and the former parent becomes a plain target. Every pre-existing relationship is preserved; nothing is dropped and nothing nests. gemma-4-12b-it has no bare entry, so it is left as is. qwen3-tts-cpp is a YAML anchor with nine merging children, so the five children that did not already override variants get an explicit empty list to stop them inheriting the parent's. Abliterated builds stay excluded: abliteration edits the weights to remove refusal behaviour, which makes them a different model rather than another build of the same one. Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-07-31 10:28:43 -04:00 · 2026-07-20 19:34:03 +02:00
parent 83a0f16a21
commit f381844403
1 changed files with 46 additions and 8 deletions
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1864,8 +1864,6 @@
      sha256: 32f7ea0600c07272547da401d460f8abbd980f3a57b69d6df87be0e2505e0b9c
      uri: https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-MTP-GGUF/resolve/main/mmproj-F32.gguf
 - name: "gemma-4-26b-a4b-it-qat"
-  variants:
-    - model: gemma-4-26b-a4b-it-qat-q4_0
  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
  urls:
    - https://huggingface.co/unsloth/gemma-4-26B-A4B-it-qat-GGUF
@@ -1975,8 +1973,6 @@
      uri: https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-gguf/resolve/main/mmproj-gemma-4-12b-it-qat-q4_0.gguf
      sha256: cb018338a7538a9814d994bfe54644c71eb7ed54e31eae2f721e45fd3c260da7
 - name: "gemma-4-e2b-it-qat-q4_0"
-  variants:
-    - model: gemma-4-e2b-it-qat-mtp
  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
  urls:
    - https://huggingface.co/google/gemma-4-E2B-it-qat-q4_0-gguf
@@ -2019,8 +2015,6 @@
      uri: https://huggingface.co/google/gemma-4-E2B-it-qat-q4_0-gguf/resolve/main/gemma-4-E2B-it-mmproj.gguf
      sha256: 021059cce659fe7f9170d5599761d7bbaf644b798dab9503aca30dc43e6beb14
 - name: "gemma-4-e4b-it-qat-q4_0"
-  variants:
-    - model: gemma-4-e4b-it-qat-mtp
  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
  urls:
    - https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf
@@ -2106,8 +2100,6 @@
      uri: https://huggingface.co/google/gemma-4-26B-A4B-it-qat-q4_0-gguf/resolve/main/gemma-4-26B-it-mmproj.gguf
      sha256: a359953a076b877db30c31dbbb4c6d93b4a6e017ee5db5784247e4d4c0dd4f3b
 - name: "gemma-4-31b-it-qat-q4_0"
-  variants:
-    - model: gemma-4-31b-it-qat-mtp
  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
  urls:
    - https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-gguf
@@ -3582,6 +3574,7 @@
  variants:
    - model: qwen3.6-35b-a3b-dflash
    - model: qwen3.6-35b-a3b-nvfp4-mtp
+    - model: qwen3.6-35b-a3b-apex
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF
@@ -3678,6 +3671,10 @@
      sha256: e92ab30c10422ff1863f0d57cf2c206ec3ae47b4903e70c672589dcb7cbec2c6
      uri: https://huggingface.co/mudler/gemma-4-26B-A4B-it-APEX-GGUF/resolve/main/gemma-4-26B-A4B-APEX-Quality.gguf
 - name: gemma-4-26b-a4b-it
+  variants:
+    - model: gemma-4-26b-a4b-it-qat
+    - model: gemma-4-26b-a4b-it-qat-q4_0
+    - model: gemma-4-26b-a4b-it-apex
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/google/gemma-4-26B-A4B-it
@@ -3722,6 +3719,8 @@
 - name: gemma-4-e2b-it
  variants:
    - model: "gemma-4-e2b-it:sglang-mtp"
+    - model: gemma-4-e2b-it-qat-q4_0
+    - model: gemma-4-e2b-it-qat-mtp
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/google/gemma-4-E2B-it
@@ -3767,6 +3766,8 @@
 - name: gemma-4-e4b-it
  variants:
    - model: "gemma-4-e4b-it:sglang-mtp"
+    - model: gemma-4-e4b-it-qat-q4_0
+    - model: gemma-4-e4b-it-qat-mtp
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/google/gemma-4-E4B-it
@@ -3809,6 +3810,9 @@
      sha256: 4c199e460410ba219a8c63930a7121154e1c70cdf66044858f767966332e5a54
      uri: huggingface://ggml-org/gemma-4-E4B-it-GGUF/mmproj-gemma-4-E4B-it-bf16.gguf
 - name: gemma-4-31b-it
+  variants:
+    - model: gemma-4-31b-it-qat-q4_0
+    - model: gemma-4-31b-it-qat-mtp
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/google/gemma-4-31B-it
@@ -6128,6 +6132,8 @@
      sha256: 0599862ac5d15cd308e1d2e368373aea6c02e25ebd1737ad4a4562a0901b0ef8
      uri: huggingface://Serveurperso/ACE-Step-1.5-GGUF/vae-BF16.gguf
 - name: vibevoice-cpp
+  variants:
+    - model: vibevoice-tts-crispasr
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/mudler/vibevoice.cpp-models
@@ -6174,6 +6180,8 @@
      sha256: b15cd8b9cae6ee2c3d20b0ee6e7bfe93f13489f8b63b6834e9bbf0dfabf6505a
      uri: huggingface://mudler/vibevoice.cpp-models/voice-en-Carter_man.gguf
 - name: vibevoice-cpp-asr
+  variants:
+    - model: vibevoice-crispasr
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/mudler/vibevoice.cpp-models
@@ -6217,6 +6225,8 @@
      uri: huggingface://mudler/vibevoice.cpp-models/tokenizer.gguf
 - &qwenttscpp_gallery
  name: qwen3-tts-cpp
+  variants:
+    - model: qwen3-tts-cpp-0.6b-base-q4
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/Serveurperso/Qwen3-TTS-GGUF
@@ -6252,6 +6262,7 @@
      uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
  name: qwen3-tts-cpp-0.6b-base-q4
+  variants: []
  description: |
    Qwen3-TTS 0.6B Base (C++ / GGML, qwentts.cpp), Q4_K_M (~0.6 GB talker).
    Streaming + voice cloning, 24kHz mono, 11 languages.
@@ -6292,6 +6303,7 @@
      uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
  name: qwen3-tts-cpp-1.7b-base-q4
+  variants: []
  description: |
    Qwen3-TTS 1.7B Base (C++ / GGML, qwentts.cpp), Q4_K_M (~1.2 GB talker).
    Streaming + voice cloning, 24kHz mono, 11 languages.
@@ -6342,6 +6354,7 @@
      uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
  name: qwen3-tts-cpp-customvoice-q4
+  variants: []
  description: |
    Qwen3-TTS 0.6B CustomVoice (C++ / GGML, qwentts.cpp), Q4_K_M. Named speakers
    via the `voice` field (serena, vivian, ryan, aiden, eric, dylan, ...).
@@ -6400,6 +6413,7 @@
      uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
  name: qwen3-tts-cpp-1.7b-customvoice-q4
+  variants: []
  description: |
    Qwen3-TTS 1.7B CustomVoice (C++ / GGML, qwentts.cpp), Q4_K_M. Named speakers
    via the `voice` field. Streaming, 24kHz mono, 11 languages.
@@ -6458,6 +6472,7 @@
      uri: huggingface://Serveurperso/Qwen3-TTS-GGUF/qwen-tokenizer-12hz-Q8_0.gguf
 - !!merge <<: *qwenttscpp_gallery
  name: qwen3-tts-cpp-1.7b-voicedesign-q4
+  variants: []
  description: |
    Qwen3-TTS 1.7B VoiceDesign (C++ / GGML, qwentts.cpp), Q4_K_M. Synthesises a
    speaker from a free-text attribute instruction - REQUIRES the `instructions`
@@ -6551,6 +6566,8 @@
      sha256: d0f4f371f80ff32ba222b1b39c192df8285c7b88986a55f954454db69618479e
      uri: huggingface://mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF/moss-tokenizer-v1_5.gguf
 - name: omnivoice-cpp
+  variants:
+    - model: omnivoice-cpp-hq
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://huggingface.co/Serveurperso/OmniVoice-GGUF
@@ -15481,6 +15498,9 @@
      sha256: fadc3e5f8d42bf7e894a785b05082e47daee4df26680389817e2093056f088ad
      uri: huggingface://unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF/Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf
 - name: gemma-3-27b-it
+  variants:
+    - model: gemma-3-27b-it-qat
+    - model: google-gemma-3-27b-it-qat-q4_0-small
  url: github:mudler/LocalAI/gallery/gemma.yaml@master
  urls:
    - https://ai.google.dev/gemma/docs
@@ -15512,6 +15532,8 @@
      sha256: 54cb61c842fe49ac3c89bc1a614a2778163eb49f3dec2b90ff688b4c0392cb48
      uri: huggingface://lmstudio-community/gemma-3-27b-it-GGUF/mmproj-model-f16.gguf
 - name: gemma-3-12b-it
+  variants:
+    - model: gemma-3-12b-it-qat
  url: github:mudler/LocalAI/gallery/gemma.yaml@master
  urls:
    - https://ai.google.dev/gemma/docs/core
@@ -15543,6 +15565,8 @@
      sha256: 30c02d056410848227001830866e0a269fcc28aaf8ca971bded494003de9f5a5
      uri: huggingface://lmstudio-community/gemma-3-12b-it-GGUF/mmproj-model-f16.gguf
 - name: gemma-3-4b-it
+  variants:
+    - model: gemma-3-4b-it-qat
  url: github:mudler/LocalAI/gallery/gemma.yaml@master
  urls:
    - https://ai.google.dev/gemma/docs/core
@@ -19541,6 +19565,8 @@
      sha256: 555b91485955bc96eb445b57dd4bbf8809aa7d8cce7c313f4f8bc5b2340896b4
      uri: huggingface://bartowski/ibm-granite_granite-3.3-2b-instruct-GGUF/ibm-granite_granite-3.3-2b-instruct-Q4_K_M.gguf
 - name: llama-3.2-1b-instruct:q4_k_m
+  variants:
+    - model: "llama-3.2-1b-instruct:q8_0"
  url: github:mudler/LocalAI/gallery/llama3.2-quantized.yaml@master
  urls:
    - https://huggingface.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF
@@ -19571,6 +19597,8 @@
      sha256: 1d0e9419ec4e12aef73ccf4ffd122703e94c48344a96bc7c5f0f2772c2152ce3
      uri: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/llama-3.2-1b-instruct-q4_k_m.gguf
 - name: llama-3.2-3b-instruct:q4_k_m
+  variants:
+    - model: "llama-3.2-3b-instruct:q8_0"
  url: github:mudler/LocalAI/gallery/llama3.2-quantized.yaml@master
  urls:
    - https://huggingface.co/hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF
@@ -20981,6 +21009,9 @@
      sha256: decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33
      uri: huggingface://HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF/smollm2-1.7b-instruct-q4_k_m.gguf
 - name: meta-llama-3.1-8b-instruct
+  variants:
+    - model: "meta-llama-3.1-8b-instruct:grammar-functioncall"
+    - model: "meta-llama-3.1-8b-instruct:Q8_grammar-functioncall"
  url: github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master
  urls:
    - https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct
@@ -29364,6 +29395,8 @@
      sha256: 236fcf372bb25f314dafa1605d84566db60ddad98b889aaa072a3108ec48ef22
      uri: huggingface://mradermacher/Arch-Router-1.5B-GGUF/Arch-Router-1.5B.Q8_0.gguf
 - name: dolphin-2.9-llama3-8b
+  variants:
+    - model: "dolphin-2.9-llama3-8b:Q6_K"
  url: github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master
  urls:
    - https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b-gguf
@@ -29979,6 +30012,8 @@
      sha256: 0cf542a127c2c835066a78028009b7eddbaf773cc2a26e1cb157ce5e09c1a2e0
      uri: huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q8_0.gguf
 - name: phi-2-chat
+  variants:
+    - model: "phi-2-chat:Q8_0"
  url: github:mudler/LocalAI/gallery/phi-2-chat.yaml@master
  urls:
    - https://huggingface.co/l3utterfly/phi-2-layla-v1-chatml
@@ -31425,6 +31460,8 @@
      sha256: afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38
      uri: https://huggingface.co/ChuckMcSneed/FLUX.1-dev/resolve/main/ae.safetensors
 - name: ideogram-4-iq4nl-ggml
+  variants:
+    - model: ideogram-4-q8_0-ggml
  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
  urls:
    - https://huggingface.co/ideogram-ai/ideogram-4-fp8
@@ -35318,6 +35355,7 @@
 - name: silero-vad
  variants:
    - model: silero-vad-ggml
+    - model: silero-vad-sherpa
  url: github:mudler/LocalAI/gallery/virtual.yaml@master
  urls:
    - https://github.com/snakers4/silero-vad